OpenSource/dify - dify - 浩瀚星图

Historique

QuantumGhost 349c3cf7b8 feat(api): Add image multimodal support for LLMNode (#17372) Enhance `LLMNode` with multimodal capability, introducing support for image outputs. This implementation extracts base64-encoded images from LLM responses, saves them to the storage service, and records the file metadata in the `ToolFile` table. In conversations, these images are rendered as markdown-based inline images. Additionally, the images are included in the LLMNode's output as file variables, enabling subsequent nodes in the workflow to utilize them. To integrate file outputs into workflows, adjustments to the frontend code are necessary. For multimodal output functionality, updates to related model configurations are required. Currently, this capability has been applied exclusively to Google's Gemini models. Close #15814. Signed-off-by: -LAN- <laipz8200@outlook.com> Co-authored-by: -LAN- <laipz8200@outlook.com>		il y a 6 mois
..
agent	fix: metadata filter not work (#19020)	il y a 6 mois
app	feat(api): Add image multimodal support for LLMNode (#17372)	il y a 6 mois
callback_handler	fix retrival resource miss in chatflow (#18307)	il y a 6 mois
entities	fix: #18744 The model order defined in position.yaml in the Model Plugin is not taking effect. (#18756)	il y a 6 mois
errors	fix(core/errors): change base class of custom exceptions to ValueError (#11955)	il y a 10 mois
extension	feat: mypy for all type check (#10921)	il y a 10 mois
external_data_tool	Enhance Code Consistency Across Repository with `.editorconfig` (#19023)	il y a 6 mois
file	feat(api): Add image multimodal support for LLMNode (#17372)	il y a 6 mois
helper	Enhance Code Consistency Across Repository with `.editorconfig` (#19023)	il y a 6 mois
llm_generator	Enhance Code Consistency Across Repository with `.editorconfig` (#19023)	il y a 6 mois
memory	fix: Update prompt message content types to use Literal and add union type for content (#17136)	il y a 6 mois
model_runtime	feat(api): Add image multimodal support for LLMNode (#17372)	il y a 6 mois
moderation	Enhance Code Consistency Across Repository with `.editorconfig` (#19023)	il y a 6 mois
ops	refactor: Refactors repository imports structure (#18901)	il y a 6 mois
plugin	Enhance Code Consistency Across Repository with `.editorconfig` (#19023)	il y a 6 mois
prompt	Enhance Code Consistency Across Repository with `.editorconfig` (#19023)	il y a 6 mois
rag	immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer (#17957)	il y a 6 mois
repositories	refactor: Refactors repository imports structure (#18901)	il y a 6 mois
tools	feat(api): Add image multimodal support for LLMNode (#17372)	il y a 6 mois
variables	fix Unicode Escape Characters (#15318)	il y a 7 mois
workflow	feat(api): Add image multimodal support for LLMNode (#17372)	il y a 6 mois
__init__.py	chore(api/core): apply ruff reformatting (#7624)	il y a 1 an
hosting_configuration.py	chore(provider_manager): Update hosted model's name (#14334)	il y a 8 mois
indexing_runner.py	fix full-doc mode document doesn't reindex after enable or un_archive (#16737)	il y a 7 mois
model_manager.py	feat(api): Add image multimodal support for LLMNode (#17372)	il y a 6 mois
provider_manager.py	fix: perferred model provider not match with provider. (#18282)	il y a 6 mois